Zero Kotlin, first Android app, a couple dozen hours with Gemini
They planned the architecture with Gemini first (dependency injection, UI components, Firebase, logging), then let its agent mode build it step by step. The app works like a charm.
Done withGeminiSpotted· by HN user codebolt· Oct 18, 2026
Result Works like a charm, neatly structured
“the app works like a charm and the code is neatly structured and easy to jump into whenever I need to make changes”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
What they did
With zero experience in Kotlin or most of the relevant libraries, they had a long discussion with Gemini about dependency injection, Material3 UI components, model-view architecture, Firebase and logging, wrote up a detailed architecture description, then let its agent mode implement the plan over several steps with a lot of tweaking along the way.
How it went
They ended up happy with the result: the app works like a charm and the code is neatly structured, finishing the project in a couple of dozen hours despite being a complete newbie to the stack.
Try it yourself with Gemini
Before writing any code, have a detailed architecture discussion with [your AI assistant] about your new project's stack, covering things like dependency injection, UI framework, data layer and logging, and capture it in a markdown spec. Then switch it to agent mode and have it implement the plan step by step, reviewing and tweaking as it goes.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.
Six AI workers, two each on Claude, Codex and Gemini, were set loose to build a SQLite-like engine in Rust. It passed 64 queries of a 1,000+ query suite, with slop like redundant buffer copies and no concurrency.
The malware was cleaned out, but a hidden backup in the database, triggered by the WordPress cron, would have brought it back. Gemini pulled the encrypted packages apart and spotted it.
They'd written one by hand years before, so they knew exactly what they wanted. In VS Code's Agent Mode, Gemini built it and refactored it into a Python decorator. One dumb corner case slipped through.
It started as a hand-drawn layout for primes by a graphic designer. Gemini and ChatGPT turned it into C++, and the ~3.1x speedup came from cache use, not new math.
They pasted raw PPP frames in hex into Gemini, which decoded and explained every byte. An hour later they knew enough to fix a Zephyr OS driver bug and submit a patch.
Never built for mobile, a parent of three, a busy life. Gemini guided the Kotlin architecture and the UI, and their first Android app was a real joy to build. Impossible a couple of years ago, they say.